A Novel Mechanical Fault Feature Selection and Diagnosis Approach for High-Voltage Circuit Breakers Using Features Extracted without Signal Processing

Abstract

The reliability and performance of high-voltage circuit breakers (HVCBs) will directly affect the safety and stability of the power system itself, and mechanical failures of HVCBs are one of the important factors affecting the reliability of circuit breakers. Moreover, the existing fault diagnosis methods for circuit breakers are complex and inefficient in feature extraction. To improve the efficiency of feature extraction, a novel mechanical fault feature selection and diagnosis approach for high-voltage circuit breakers, using features extracted without signal processing is proposed. Firstly, the vibration signal of the HVCBs’ operating system, which collects the amplitudes of signals from normal vibration signals, is segmented by a time scale, and obviously changed. Adopting the ensemble learning method, features were extracted from each part of the divided signal, and used for constructing a vector. The Gini importance of features is obtained by random forest (RF), and the feature is ranked by the features’ importance index. After that, sequential forward selection (SFS) is applied to determine the optimal subset, while the regularized Fisher’s criterion (RFC) is used to analyze the classification ability. Then, the optimal subset is input to the hierarchical hybrid classifier, and based on a one-class support vector machine (OCSVM) and RF for fault diagnosis, the state is accurately recognized by OCSVM. The known fault types are identified using RF, and the identification results are calibrated with OCSVM of a particular fault type. The experimental proves that the new method has high feature extraction efficiency and recognition accuracy by the measured HVCBs vibration signal, while the unknown fault type data of the untrained samples is effectively identified.

Mechanical Fault Diagnosis of a High Voltage Circuit Breaker Based on High-Efficiency Time-Domain Feature Extraction with Entropy Features

“…To verify the diagnosis efficiency and classification accuracy of the new method under the noise environment, the vibration signal of the circuit breaker with a signal-to-noise ratio of 30 dB after adding white noise was taken as the experimental object. The new method and the method in [ 15 , 17 , 34 ] were used to carry out fault diagnosis, respectively, and the effectiveness and robustness of different methods were compared. Among them, literature [ 15 , 17 ] uses the time–frequency analysis method, without feature selection.…”

“…Among them, literature [ 15 , 17 ] uses the time–frequency analysis method, without feature selection. Both the new method and the reference [ 34 ] adopt the feature extraction method based on time-domain segmentation, and both of them contain feature selection links, but the scale, type, and number of features in time-domain segmentation are also different. In the experiment, the data and results of feature extraction and classification in the experiment are shown in Table 4 .…”

“…In reference [ 17 ], the time–frequency domain analysis method of VMD is easy to be affected by the number of decomposition layers K and penalty coefficient P , and the error of parameter setting will affect the final feature extraction effect. In reference [ 34 ], the time-domain features of the original signal are extracted directly, which improves the efficiency of feature extraction. However, the time-domain segmentation scale is narrow, the number of features in the original feature set is large, and the type of entropy features is small.…”

“…A multi-layer classifier is used in reference [ 17 ], which needs to be judged many times in the process of fault diagnosis and has poor anti-noise ability and low classification accuracy. OCSVM-RF-OCSVM used in reference [ 34 ] is a combination of two classifiers. The accuracy of fault diagnosis is higher than that of using OCSVM or RF alone.…”

Important Factors for Consideration during the Specification of SF6 Circuit Breakers for High Voltage Generators

“…There may be damage to the control cables if the generator is switched off and then immediately switched on to the network without fulfilling the synchronization conditions [14][15][16][17]. Table 4 shows the values recorded during a time of 60 ms for I rms (effective value of the current) depending on the time during the considered case [14].…”